Monitoring geometrical properties of word embeddings for detecting the emergence of new topics

TL;DR

This paper introduces a method for early detection of slowly emerging topics by monitoring geometrical properties of word embeddings, demonstrating improved performance over existing methods on public datasets.

Contribution

It proposes a novel approach that uses geometrical properties of word embeddings to detect emerging topics earlier than traditional methods.

Findings

Outperforms state-of-the-art methods on press and scientific datasets

Provides a quantitative framework for evaluating early topic detection

Effectively detects weak signals indicating new topic emergence

Abstract

Slow emerging topic detection is a task between event detection, where we aggregate behaviors of different words on short period of time, and language evolution, where we monitor their long term evolution. In this work, we tackle the problem of early detection of slowly emerging new topics. To this end, we gather evidence of weak signals at the word level. We propose to monitor the behavior of words representation in an embedding space and use one of its geometrical properties to characterize the emergence of topics. As evaluation is typically hard for this kind of task, we present a framework for quantitative evaluation. We show positive results that outperform state-of-the-art methods on two public datasets of press and scientific articles.